61
First AI model that translates 100 languages without relying on English
Facebook AI is introducing M2M-100, the first multilingual machine translation model that can translate between any pair of 100 languages without relying on English data.
Topics /
AI & Machine Learning
The most popular blog posts about ai & machine learning on Hacker News. 212 posts.
62
Adventures in Improving AI Economics
AI has enormous potential to disrupt markets that have traditionally been out of reach for software. These markets – which have relied on humans to navigate natural language, images, and physical space – represent a huge opportunity, potentially worth trillions of dollars globally. However, as we discussed in our…
63
Cool Machine Learning Books
awhile ago i posted my list of cool machine learning books , but it's been awhile so it's probably time to update it...
64
65
Introduction to Reinforcement Learning (2015)
Build AI responsibly to benefit humanity
66
Standardizing OpenAI’s deep learning framework on PyTorch
We are standardizing OpenAI’s deep learning framework on PyTorch.
67
68
69
Illustrated FixMatch for semi-supervised learning
Learn how to leverage unlabeled data using FixMatch for semi-supervised learning
70
GPT-3 Creative Fiction
Creative writing by OpenAI’s GPT-3 model, demonstrating poetry, dialogue, puns, literary parodies, and storytelling. Plus advice on effective GPT-3 prompt programming & avoiding common errors.
71
Online speech recognition with wav2letter anywhere
We have open-sourced wav2letter@anywhere, an inference framework for online speech recognition that delivers state-of-the-art performance.
72
Ray Tracing Essentials, Part 1: Basics of Ray Tracing
Ray Tracing Essentials is a seven-part video series hosted by the editor of Ray Tracing Gems, NVIDIA’s Eric Haines.
73
AI model detects asymptomatic Covid-19 infections through phone-recorded coughs
An artificial intelligence model can detect people who are asymptomatic with Covid-19, through cellphone-recorded coughs. The work was led by Brian Subirana and colleagues at the MIT Auto-ID Lab.
74
Which GPUs to get for deep learning
Here, I provide an in-depth analysis of GPUs for deep learning/machine learning and explain what is the best GPU for your use-case and budget.
75
SpaCy v3.0 Nightly
spaCy v3.0 is a huge release! It features new transformer-based pipelines that get spaCy's accuracy right up to the current state-of-the-art, and a new workflow system to help you take projects from prototype to production. It's much easier to configure and train your pipeline, and there are lots of new and improved…
76
Why GPT-3 Matters
The sheer scale of the new GPT-3 model is hard to overstate; it’s an entire order of magnitude larger than Microsoft’s already-massive 17B parameter Turing-NLG.[1] Loading the entire model’s weights
77
Quantum supremacy, now with BosonSampling
Update (12/5): The Google team, along with Gil Kalai, have raised questions about whether the results of the new BosonSampling experiment might be easier to spoof classically than the USTC team tho…
78
Traffic Prediction with Advanced Graph Neural Networks
By partnering with Google, DeepMind is able to bring the benefits of AI to billions of people all over the world. From reuniting a speech-impaired user with his original voice, to helping users discover personalised apps, we can apply breakthrough research to immediate real-world problems at a Google scale. Today…
79
80
Visual Introduction to Self Supervised Learning
A visual introduction to self-supervised learning methods for visual representations.
81
Microsoft Zero and DeepSpeed: Memory Efficient Large Neural Network Training
The latest trend in AI is that larger natural language models provide better accuracy; however, larger models are difficult to train because of cost, time, and ease of code integration. Microsoft is releasing an open-source library called DeepSpeed, which vastly advances large model training by improving scale, speed…
82
83
84
85
86
How much did AlphaGo Zero cost? (2018)
Answer: probably around $35 million.
87
88
Rethinking Attention with Performers
Posted by Krzysztof Choromanski and Lucy Colwell, Research Scientists, Google Research Transformer models have achieved state-of-the-art results ac...
89
Bringing the Mona Lisa Effect to Life with Tensorflow.js
Urban legend says that Mona Lisa's eyes will follow you as you move around the room. This interactive digital portrait brings the phenomenon to life..
90
Score matching with Langevin Sampling: a new contender to GANs
Last year, Yang Song, a graduate student at Stanford, showed an entirely new way of generating data based on denoising score matching with Annealed Langevin sampling (DSM-ALS). The paper showed tha…